pseo-orchestrate
npx skills add https://github.com/lisbeth718/pseo-skills --skill pseo-orchestrate
Agent 安装分布
Skill 文档
pSEO Orchestrator
Coordinate the execution of all pseo-* skills in the correct dependency order to implement or validate a complete programmatic SEO system.
Skill Dependency Graph
pseo-discovery (0) â what should we build? what data exists?
â
â¼
pseo-audit (1) â is the codebase ready for what we want to build?
â
â¼
pseo-scale (1.5) â CONDITIONAL: only if 10K+ pages planned
â
â¼
pseo-data (2)
â
ââââââââââââââââ
â¼ â¼
pseo-templates (3) pseo-linking (4)
â â
ââââââââ¬ââââââââ
â
ââââââââ´ââââââââ
â¼ â¼
pseo-metadata (5) pseo-schema (6) â parallel: both read from data layer
â â
ââââââââ¬ââââââââ
â
ââââââââ´ââââââââ
â¼ â¼
pseo-performance pseo-llm-visibility â parallel: independent optimizations
(7) (8)
â â
ââââââââ¬ââââââââ
â¼
pseo-quality-guard (9)
Note: metadata and schema are independent of each other â both read from the data layer and render into templates. Run them in parallel in Phase 4.
Note: pseo-scale only applies when discovery identifies 10K+ pages. It runs after audit to set up database infrastructure, data sufficiency gating, and CDN architecture before the data layer is built. At < 10K pages, skip it entirely.
Execution Modes
full (default)
Run the complete pipeline: discover â audit â implement â validate.
discover-only
Run only pseo-discovery. No code changes. Use when the user doesn’t yet know what to build.
audit-only
Run pseo-audit and pseo-quality-guard. No code changes. Assumes discovery is done.
implement
Skip discovery and audit, go straight to implementation (assumes both were already done).
validate
Run only pseo-quality-guard against the existing implementation.
Full Pipeline Procedure
Phase 0: Discovery
- Run pseo-discovery with scope
all - Present the discovery report: data assets found, proposed page types, rejected candidates
- Ask the user to confirm which page types to pursue
- If data enrichment is needed, flag it â implementation cannot produce quality pages without sufficient data
Phase 1: Audit
- Run pseo-audit with scope
full, informed by the discovery output (what page types are planned) - Present findings to the user
- Ask the user to confirm which areas to implement
- Create a prioritized implementation plan based on audit results
Phase 1.5: Scale Infrastructure (conditional â 10K+ pages only)
- Run pseo-scale to set up database, sufficiency gating, CDN, and monitoring
- Migrate existing data to database if moving from file-based storage
- Compute data sufficiency scores and gate thin combinations
Phase 2: Data Foundation
- Run pseo-data to set up or refactor the data architecture
- Verify data layer exports are complete and typed
- Validate slug uniqueness and data integrity
Phase 3: Page Structure (parallel where possible)
- Run pseo-templates to create or refactor page templates and routing
- Run pseo-linking to build internal linking, breadcrumbs, and hub pages
- Verify all routes generate correctly and no 404s exist
Phase 4: SEO Tags
- Run pseo-metadata to implement dynamic metadata on all templates
- Run pseo-schema to add JSON-LD structured data to all templates
- Verify metadata and schema render correctly on sample pages
Phase 5: Optimization
- Run pseo-performance to optimize build times, CWV, and caching
- Run pseo-llm-visibility to optimize for AI citation (llms.txt, AI crawlers, content chunking, entity optimization)
- Run a build to verify it completes successfully at current scale
- Check bundle size and rendering performance
Phase 6: Validation
- Run pseo-quality-guard with scope
all(ordeltaat 10K+ pages) - Present quality report to the user
- Fix any critical issues flagged by the quality guard
- Re-run quality guard to confirm all issues resolved
Decision Points
At each phase transition, check with the user:
- Phase 0â1: “Here are the pSEO opportunities. Which page types should we build?”
- Phase 1â1.5: “The audit found these issues. Scale target is N pages â do we need scale infrastructure?” (only if 10K+)
- Phase 1.5â2: “Database and gating are set up. Proceed with data architecture?”
- Phase 1â2: “The audit found these issues. Proceed with implementation?” (if < 10K, skip 1.5)
- Phase 3â4: “Templates and linking are set up. Ready for metadata and schema?”
- Phase 5â6: “Performance and LLM visibility optimizations applied. Ready for final validation?”
Progress Tracking
Track and report progress as:
Phase 0: Discovery [â] Complete â 3 page types confirmed, 50K pages planned
Phase 1: Audit [â] Complete
Phase 1.5: Scale Infra [â] Complete (DB, gating, CDN) â skipped if < 10K
Phase 2: Data [â] Complete
Phase 3: Structure [â] In Progress (templates done, linking in progress)
Phase 4: SEO Tags [ ] Pending
Phase 5: Optimization [ ] Pending (performance + LLM visibility)
Phase 6: Validation [ ] Pending
Important Rules
- Never skip the discovery phase on a new project (unless user already knows exactly what pages to build)
- Never skip the audit phase on a new project (unless user explicitly says to)
- Always run pseo-quality-guard as the final step
- If quality guard finds critical issues, fix them before declaring success
- Commit changes at logical checkpoints (after each phase)
- Keep the user informed at each phase transition
Framework Note
All code examples across the pseo-* skills use Next.js App Router patterns by default. The concepts, data structures, and SEO principles are framework-agnostic and apply equally to Astro, Nuxt, Remix, SvelteKit, or any SSG/SSR framework. When working with a non-Next.js project, adapt the framework-specific APIs (routing, metadata, static generation) to the equivalent in the target framework.
What This Skill Does NOT Do
- Does not choose a framework (assumes one is already in place or user will decide)
- Does not create content (assumes data/content exists or user will provide it)
- Does not deploy the site
- Does not set up CI/CD
- Does not configure hosting or DNS